RemoteDPL: A Semi-Supervised Object Detector With Dense Pseudo-Labels for Remote Sensing

Deep learning-based object detection (OD) has seen substantial advancements; however, its practical deployment is often constrained by the need for large-scale labeled datasets. This limitation becomes even more critical in remote sensing imagery, where objects are densely distributed and exhibit significant scale variations. To address these challenges, we introduce dense pseudo-labels based SSOD method (RemoteDPL), a novel semi-supervised OD (SSOD) framework that leverages dense pseudo-labels (DPLs) and multiscale learning. RemoteDPL offers three key contributions. First, a fusion module is designed to dynamically integrate spatial and channel features across scales, improving detection across varied object sizes. Second, an instance density prediction branch is introduced to support pseudo-label mining, enhancing detection performance in densely populated regions. Finally, we propose a two-stage pseudo-label filtering strategy that first selects “pending” class predictions and then refines them using a joint confidence score based on both classification and density information. Extensive experiments on the DOTA-v1.0 and NWPU datasets confirm the effectiveness of RemoteDPL, demonstrating its clear advantage over existing state-of-the-art (SOTA) SSOD methods. On the NWPU dataset, RemoteDPL outperforms the SOTA baseline by +3.44%, +1.10%, and +1.62% under the settings of data labeled with 30%, 40%, and 50%, respectively, highlighting its strong capability in low-label remote sensing scenarios.